The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The documentation in README.md and AGENTS.md guides the user and agent to install or update skill components using npx skills add and npm install for packages within the metyatech organization. These are recognized as legitimate vendor resources for this skill's ecosystem.
[PRIVILEGE_ESCALATION]: The AGENTS.md rule module instructs the agent to use sudo directly when elevated privileges are required for task completion, prioritizing native commands over shell wrappers. This is a behavioral guideline for the agent's operating environment.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external educational documents such as syllabi and lesson plans.
Ingestion points: Workflow steps in SKILL.md and references/patterns.md describe the ingestion of teaching artifacts.
Boundary markers: None identified in the skill instructions.
Capability inventory: The environment configuration in AGENTS.md allows the agent to execute shell commands, manage git repositories, and perform file system operations.
Sanitization: No specific sanitization or filtering logic is defined for the educational content being processed.
[COMMAND_EXECUTION]: The AGENTS.md file defines a "Session gate" requiring the execution of compose-agentsmd at the start of every interaction, along with mandatory usage of task-tracker and thread-inbox for state management. These tools are part of the author's internal engineering standards.

teaching-style-patterns